Job Overview
We're seeking a developer with substantial expertise in LLM systems to architect and deploy production-grade AI applications, including assistants and enterprise automation platforms, while providing technical mentorship across the team.
Key Responsibilities
- Architect LLM applications using OpenAI, Claude, Gemini, and open-source models.
- Design enterprise RAG pipelines with vector databases.
- Implement advanced prompt engineering and agentic workflows.
- Perform model fine-tuning using LoRA, QLoRA, and PEFT techniques.
- Lead LLM backend integration using Python or Node.js.
- Optimize inference performance and token costs.
- Build secure AI APIs with FastAPI, Flask, or NestJS.
- Deploy services via Docker, Kubernetes, and cloud platforms.
- Implement monitoring and evaluation metrics.
- Ensure compliance with HIPAA, GDPR, and SOC 2 standards.
- Conduct code reviews and mentor junior staff.
- Collaborate cross-functionally on production systems.
Required Qualifications
- Bachelor's or Master's degree in Computer Science, AI, ML, or a related field.
- 6–8 years in AI/ML, NLP, or backend engineering.
- 3+ years hands-on experience with LLM systems.
Nice-to-Have Skills
- Multi-agent systems experience (AutoGen, CrewAI, AutoGPT).
- MLOps tools knowledge (MLflow, Weights & Biases, Kubeflow).
- Enterprise security and data encryption experience.
- Healthcare, BFSI, or SaaS domain expertise.